Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 885 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 5-way 5-shot Few-Shot Classification | BSCD-FSL Suite (ChestX, ISIC, EuroSAT, CropDisease, CUB, Cars, Places, Plantae) 1.0 (test) | 30 | Mar 19, 2026 | ||
| Dataset Distillation | CIFAR-100 10 images/class (test) | 30 | Feb 26, 2026 | ||
| AWGN removal | McMaster color (test) | 30 | Feb 26, 2026 | ||
| Grayscale Image Denoising | Set12 | 30 | Mar 30, 2026 | ||
| Rolling Shutter SLAM | TUM-RSVI (10 sequences) | 30 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL VOC Original (Full) 2012 (train) | 30 | Feb 26, 2026 | ||
| Novel View Synthesis | Ricoh360 (test) | 30 | Jun 30, 2026 | ||
| Object Detection | COCO 1% labeled 2017 (val train) | 30 | Feb 26, 2026 | ||
| Image Classification | SVHN 1.0 (test) | 30 | Feb 26, 2026 | ||
| Semantic Segmentation | DELIVER | 30 | Mar 4, 2026 | ||
| Adversarial Attack | Pascal (val) | 30 | Feb 26, 2026 | ||
| Adversarial Attack | Pascal VOC | 30 | Feb 26, 2026 | ||
| Adversarial Attack | Pascal | 30 | Feb 26, 2026 | ||
| Binary Classification | Higgs (test) | 30 | Feb 26, 2026 | ||
| Natural Language Inference | MNLI mm | 30 | Feb 27, 2026 | ||
| Video Question Answering | AGQA v2 (test) | 30 | Feb 26, 2026 | ||
| Entity Matching | Fodors-Zagats | 30 | Jun 30, 2026 | ||
| Node Classification | Chameleon (10 different splits) | 30 | Feb 26, 2026 | ||
| Long-form Transcription | Earnings-22 | 30 | Jun 9, 2026 | ||
| Image Classification | FieldGuide-2 (test) | 30 | Feb 26, 2026 | ||
| Traveling Salesman Problem | TSP N=50 10,000 instances (test) | 30 | Jun 23, 2026 | ||
| Adversarial Attack | TinyImageNet | 30 | Feb 26, 2026 | ||
| Segmentation | BraTS | 30 | Feb 26, 2026 | ||
| eXtreme Multi-label Classification | Wiki 500K | 30 | Feb 26, 2026 | ||
| Absolute 3D Human Pose Estimation (MRPE) | H36M (test) | 30 | Feb 26, 2026 |